Packages
Integrates the Milvus vector database with LlamaIndex for storing and retrieving vector embeddings in LLM applications.
Install only if you have Milvus available or plan to deploy it; this is a connector, not a standalone vector store.
Integrates Pinecone vector database with LlamaIndex for storing and retrieving embeddings in RAG and semantic search applications.
Integrates PostgreSQL with pgvector extension as a vector store backend for LlamaIndex, supporting multiple query modes including similarity search, hybrid retrieval, BM25 sparse search, full-text search, and maximal marginal relevance.
Integrates Qdrant vector database with LlamaIndex for storing and retrieving embeddings in RAG and semantic search applications.
Integrates Redis as a vector store backend for LlamaIndex, enabling storage and retrieval of vector embeddings in Redis for RAG and semantic search applications.
Install only if you intend to use Redis as your vector store backend; it is not useful standalone without LlamaIndex and a Redis instance.
An async-first, event-driven framework for orchestrating multi-step AI workflows with state management and built-in observability instrumentation.
Provides a CLI and Python interface to download, manage, and run Meta's Llama language models, handling authentication, model listing, verification, and local checkpoint management.
However, the aging maintenance status (no release in ~9 months, last commit in Feb 2026) suggests the project may be in maintenance mode; verify that it still works…
LlamaParse parses complex documents (PDFs, Word, Excel, PowerPoint, HTML) into structured text, markdown, or JSON optimized for RAG and LLM workflows, with built-in support for tables, images, and custom parsing instructions.
Python client library for interacting with Llama Stack REST API, providing type-safe synchronous and asynchronous access to inference, chat, and model management endpoints.
LLaMA Factory provides a unified framework for fine-tuning 100+ large language models through CLI and web UI, supporting multiple training methods and model architectures with minimal setup.
Enforces structured output from large language models by computing token masks that constrain decoding to valid context-free grammars, JSON schemas, or regular expressions with minimal per-token overhead.
Provides doubly and singly linked list data structures as C extension modules for CPython, optimized for fast insertions and deletions in the middle of sequences.
LLM is a CLI tool and Python library for running prompts against Large Language Models from OpenAI, Anthropic, Google, Meta, and dozens of other providers, both via remote APIs and locally-installed models.
A plugin for the LLM command-line tool that adds access to Anthropic's Claude models, including support for image and PDF attachments, web search and fetch, code execution, and structured output schemas.
Install it if you use LLM and want Claude access; the only prerequisite is an Anthropic API key.
A plugin for the llm command-line tool that provides access to GitHub Models, a free service offering many AI language models via the Azure AI Inference SDK.
Install it if you want to experiment with or integrate GitHub Models into command-line workflows or GitHub Actions without cost.
LLM Guard provides input and output scanning for Large Language Models to detect and prevent prompt injection, data leakage, harmful language, and other security threats.
No—not for new projects.
A plugin that extends LLM to access OpenAI models via the Responses API, enabling use of models like o1-pro that are unavailable through LLM's default Chat Completions implementation.
However, the aging maintenance status and preview designation mean you should expect possible API changes and verify that your target models are actually available…
Executes code generated by large language models in isolated container environments (Docker, Kubernetes, or Podman) with configurable security policies, resource limits, and support for Python, JavaScript, Java, C++, Go, and R.
However, verify the unclear license terms before use in proprietary contexts, and ensure your deployment environment supports containerization.
llmcompressor optimizes large language models for efficient deployment by applying quantization, pruning, and other compression techniques compatible with vLLM inference.
LLMLingua compresses prompts by identifying and removing non-essential tokens, reducing input length to LLMs by up to 20x while preserving task performance and lowering API costs.
Provides LLVM testing utilities like FileCheck and split-file as standalone Python tools, enabling runtime builds to access these testing features without requiring a full LLVM bootstrap build.
llvmlite provides a lightweight Python binding to LLVM's IR builder, optimizer, and JIT compiler APIs, enabling you to write JIT compilers and code generators without needing the full LLVM C++ API surface.
Unified framework for evaluating generative language models against over 60 standard academic benchmarks with hundreds of task variants, supporting multiple model backends and inference engines.
Install only if you have a model backend in mind and Python >=3.10.
Constrains language model token generation to enforce JSON Schema, regex, or other structured output formats, ensuring models produce valid formatted output at every generation step.
LMCache is a KV cache management layer that stores, reuses, and monitors transformer key-value caches across LLM inference requests, reducing time-to-first-token and improving throughput for long-context workloads.
Provides a Python binding to LMDB (Lightning Memory-Mapped Database), a fast key-value store based on memory-mapped files for efficient data access and storage.
Lmfit provides non-linear least-squares minimization and curve fitting with named, constrained parameters that can be bounded, fixed, or linked by expressions.
lml provides a lazy plugin management system that discovers and loads plugins on demand rather than at startup, designed to defer loading of plugins with heavy external dependencies.
However, the aging maintenance status means you should verify it works with your target Python versions before committing to it as a core dependency.
Python SDK that traces, evaluates, and analyzes LLM application behavior through automatic and manual instrumentation, with built-in support for OpenTelemetry and popular LLM libraries.
Install it if you need tracing and evaluation for LLM products and have access to a Laminar backend; skip it if you have no observability backend or prefer a…
A thin proxy server that routes Claude Code requests through Laminar tracing infrastructure, associating trace and span IDs to maintain observability context across distributed calls.
However, verify the proprietary license terms first.
Python SDK for interacting with LM Studio, a local LLM application, enabling text completion and chat interactions with loaded language models via WebSocket.
However, the 357-day gap since the last release and unclear license terms warrant caution: verify license compliance before commercial use, and expect slower…
Provides convenience functions for mapping, filtering, grouping, and transposing iterables—operations that complement Python's built-in generator functions.
Automatically loads environment variables from a .env file into your application when a specific environment variable is set, without requiring explicit code changes.
Loads and converts images between multiple formats—numpy arrays, PIL objects, file paths, URLs, and base64 strings—with automatic format detection.
Python wrapper for the Lob.com API, providing object-oriented access to print-mail services including postcards, letters, checks, and address verification.
However, verify that the package still works with Lob's current API and that your target Python version is supported before committing to it in production.
Implements local windowed attention for transformer models, allowing efficient attention computation over fixed-size windows rather than full sequences.
However, the 394-day gap since the last release and aging maintenance status suggest it is stable but not actively developed—suitable for production use in…
Converts crontab expressions from a local timezone into UTC-equivalent crontabs, accounting for Daylight Saving Time by generating multiple UTC schedules.
LocalStack is a command-line tool that emulates AWS cloud services locally, allowing you to develop and test cloud applications on your laptop or in CI without hitting real AWS.
However, the abandoned maintenance status (archived repo, last commit 2026-03-23) is a significant concern: verify that the version you need is stable and that…
A Python client that wraps boto3 to redirect AWS API calls to a local LocalStack instance for development and testing without hitting real AWS.
Provides extensions and additional functionality for LocalStack, a local AWS service emulator that runs in Docker.